Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prepositions or conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.71
    SourceFile
    -0.63
    tons
    -0.61
    eous
    -0.58
    Pacific
    -0.57
    Tes
    -0.56
     Everest
    -0.55
     rogue
    -0.55
     737
    -0.54
    ··
    -0.52
    POSITIVE LOGITS
    stood
    0.80
    glomer
    0.71
     importantly
    0.67
    productive
    0.64
    advertising
    0.61
    ertain
    0.61
    jured
    0.61
    jac
    0.60
    ked
    0.60
     consequently
    0.59
    Act Density 0.201%

    No Known Activations